Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5996
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of cultivation activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to agricultural processes, specifically the cultivation of plants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jet
    -0.81
    911
    -0.81
     Daytona
    -0.77
     Avenger
    -0.77
     DB
    -0.76
     911
    -0.74
     Uh
    -0.72
     Dunk
    -0.71
     Thor
    -0.70
     Titanic
    -0.69
    POSITIVE LOGITS
     cultivate
    3.13
     cultivating
    3.04
     cultivation
    3.00
     cultivated
    2.99
     cultiv
    2.43
     growers
    1.62
     nurture
    1.51
     nurt
    1.47
    cult
    1.44
    grow
    1.41
    Activations Density 0.041%

    No Known Activations